You're looking at a specific version of this model. Jump to the model overview.
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| prompt |
string
|
Text prompt for generation, editing, or understanding
|
|
| image |
string
|
Input image for editing or understanding tasks
|
|
| task |
string
(enum)
|
text-to-image
Options: text-to-image, image-editing, image-understanding |
Task to perform
|
| enable_thinking |
boolean
|
False
|
Enable chain-of-thought reasoning for better results
|
| cfg_text_scale |
number
|
4
Min: 1 Max: 20 |
Text guidance scale for how closely to follow the prompt
|
| cfg_img_scale |
number
|
1.5
Min: 1 Max: 10 |
Image guidance scale for preserving input image details
|
| num_inference_steps |
integer
|
50
Min: 1 Max: 100 |
Number of denoising steps
|
| timestep_shift |
number
|
3
Min: 1 Max: 10 |
Distribution of denoising steps between composition and details
|
| cfg_renorm_type |
string
(enum)
|
global
Options: global, local, text_channel |
CFG renormalization method
|
| cfg_renorm_min |
number
|
1
Max: 1 |
Minimum CFG renorm value
|
| seed |
integer
|
Random seed for reproducible results
|
|
| output_format |
string
(enum)
|
webp
Options: webp, jpg, png |
Output image format
|
| output_quality |
integer
|
90
Min: 1 Max: 100 |
Image compression quality for lossy formats
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'description': 'Output from BAGEL model inference',
'properties': {'image': {'format': 'uri', 'title': 'Image', 'type': 'string'},
'text': {'title': 'Text', 'type': 'string'}},
'title': 'BagelOutput',
'type': 'object'}